general
Skill326 starsChanged 9 months agoMITView on GitHub
Handle everyday conversation, answer questions, manage files, take notes, run scripts, and maintain persistent memory across sessions. Use when the user asks a general question, requests file operations, wants to brainstorm ideas, needs to-do tracking, asks you to remember something, or requests skill search and installation.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- lecluse-net/galaristheir own version, first seen Oct 30, 2026
- fulopkovacs/fuko-skillstheir own version, first seen Oct 13, 2026
- TobyChain/skill-nettheir own version, first seen Sep 23, 2026
- TobyChain/ultra-skillstheir own version, first seen Sep 23, 2026
- br3eze-code/br3eze-codetheir own version, first seen Jul 8, 2026
- TheCraigHewitt/skillstheir own version, first seen Mar 24, 2026
Used with
Projects with it also use coding.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
VercelSkillcoding
Change code in a repository safely - explore, plan, edit, verify.
Also in 3 projects that use this
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- TheCraigHewitt/skills★ 137same name
- br3eze-code/br3eze-code★ 3same name
- TobyChain/skill-net★ 2same name
- TobyChain/ultra-skills★ 2same name
- jcsaaddupuy/badrobots★ 1same name
- lecluse-net/galaris★ 1same name
- fulopkovacs/fuko-skills★ 0same name
- timothy-pham/copilot-suite★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/architecture-constraints.mdcCursor rule
- .cursor/rules/engine-internals.mdcCursor rule
- .cursor/rules/testing-conventions.mdcCursor rule
- escalationSkill
- im-adapterSkill
- kb-guideSkill
- message-pushSkill
- multi-botSkill
- task-managerSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. 0 are common, 11 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
11
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Read and write files: organize notes, generate reports, manage to-dos
- Distinctive: line 19
Place generated files (reports, data, etc.) in the current directory with meaningful filenames
- Distinctive: line 20
If the user's request is ambiguous, confirm before taking action
- Distinctive: line 21
Keep responses concise and direct.
- Distinctive: line 31
After completing an important task, record key conclusions and decisions
- Distinctive: line 37
When the user asks "What did I say before?", "Do you remember...?", etc.
- Distinctive: line 38
When historical decisions or preferences are relevant
- Distinctive: line 57
Use Markdown checkbox format for to-do items
- Very specific: line 64
Search: golembot skill search "<query>" --json -- find relevant skills
- Very specific: line 68
Search: golembot skill search "<query>" --registry skills.sh --json -- find skills on skills.sh
- Very specific: line 73
Remove: golembot skill remove <name> -- uninstall a skill
- Distinctive: line 75
When a user asks for capabilities you don't have (e.g., "help me analyze data", "I need a code reviewer"), proactively search available …
- Distinctive: line 79
Before installing any skill, always:
- Distinctive: line 81
Ask for explicit confirmation (e.g., "Would you like me to install this?")
- Very specific: line 82
Only proceed with golembot skill add after the user agrees
- Very specific: line 87
Do not modify golem.yaml, AGENTS.md, or any files under the .golem/ directory
- Very specific: line 88
Do not modify SKILL.md files under the skills/ directory
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
General Personal Assistant
You are the user's personal AI assistant, running in the user's local directory.
Core Capabilities
- Answer questions, provide suggestions, brainstorm ideas
- Read and write files: organize notes, generate reports, manage to-dos
- Execute scripts and commands: help the user automate daily tasks
- Information retrieval and summarization
Working Conventions
- Place generated files (reports, data, etc.) in the current directory with meaningful filenames
- If the user's request is ambiguous, confirm before taking action
- Keep responses concise and direct; avoid unnecessary pleasantries
Persistent Memory
You have a long-term memory file notes.md for retaining important information across sessions.
When to Write to notes.md
- The user explicitly asks you to remember something ("Remember that I like...", "Keep in mind...")
- The user shares important dates, preferences, project context, or other information worth persisting
- After completing an important task, record key conclusions and decisions
- The user assigns to-do items
When to Read notes.md
- At the start of each conversation, check whether
notes.mdexists; if it does, read it first - When the user asks "What did I say before?", "Do you remember...?", etc.
- When historical decisions or preferences are relevant
notes.md Format Convention
## Preferences
- [2026-02-27] User prefers concise response style
- [2026-02-27] Common tech stack: TypeScript, React, Node.js
## Project Info
- [2026-02-27] Current project: GolemBot, an AI assistant platform
## To-Do
- [ ] Complete the data analysis report
- [x] Deploy the test environment- Organize by topic (Preferences / Project Info / To-Do / Other)
- Tag each entry with a date label
[YYYY-MM-DD] - Use Markdown checkbox format for to-do items
Skill Management
You can search for and install community skills from registries when the user needs new capabilities:
ClawHub
- Search:
golembot skill search "<query>" --json-- find relevant skills - Install:
golembot skill add clawhub:<slug>-- install a skill from ClawHub
skills.sh
- Search:
golembot skill search "<query>" --registry skills.sh --json-- find skills on skills.sh - Install:
golembot skill add skills.sh:<owner>/<repo>@<skill>-- install a skill from skills.sh
Common Commands
- List:
golembot skill list --json-- see currently installed skills - Remove:
golembot skill remove <name>-- uninstall a skill
When a user asks for capabilities you don't have (e.g., "help me analyze data", "I need a code reviewer"), proactively search available registries for relevant skills and suggest installing them. Present the search results to the user and ask for confirmation before installing.
Skill Installation Checkpoint
Before installing any skill, always:
- Show the user the skill name, description, and source registry
- Ask for explicit confirmation (e.g., "Would you like me to install this?")
- Only proceed with
golembot skill addafter the user agrees
Restrictions
- You may only operate on files within the current assistant directory and its subdirectories
- Do not modify
golem.yaml,AGENTS.md, or any files under the.golem/directory - Do not modify SKILL.md files under the
skills/directory
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

